Create a chat completion | Panicly Documentation

Sends an OpenAI-compatible chat completion request through Panicly. Panicly authenticates the project key, evaluates controls, records a decision, and then forwards approved traffic upstream.

Authentication

AuthorizationBearer

Panicly project key supplied as Authorization: Bearer pk_live_....

x-panicly-keystring

Panicly project key supplied directly in the x-panicly-key header.

Request

This endpoint expects an object.

modelstringRequired

Provider model identifier.

messageslist of objectsRequired

max_tokensintegerOptional

Maximum tokens requested from the provider.

temperaturedoubleOptional

Response

Provider response returned through Panicly.

idstring

objectstring

createdinteger

modelstring

choiceslist of maps from strings to any

Errors

401

Unauthorized Error

402

Payment Required Error

403

Forbidden Error

$	curl -X POST https://panicly.vercel.app/v1/chat/completions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "openrouter/auto",
>	"messages": [
>	{
>	"role": "user",
>	"content": "Write one sentence about protected AI spend."
>	}
>	],
>	"max_tokens": 64
>	}'

1	{
2	"id": "chatcmpl_panicly_example",
3	"object": "chat.completion",
4	"created": 1779993600,
5	"model": "openrouter/auto",
6	"choices": [
7	{
8	"index": 0,
9	"message": {
10	"role": "assistant",
11	"content": "Panicly blocks risky model traffic before it can create upstream spend."
12	},
13	"finish_reason": "stop"
14	}
15	]
16	}

$	curl -X POST https://panicly.vercel.app/v1/chat/completions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "openrouter/auto",
>	"messages": [
>	{
>	"role": "user",
>	"content": "Write one sentence about protected AI spend."
>	}
>	],
>	"max_tokens": 64
>	}'

1	{
2	"id": "chatcmpl_panicly_example",
3	"object": "chat.completion",
4	"created": 1779993600,
5	"model": "openrouter/auto",
6	"choices": [
7	{
8	"index": 0,
9	"message": {
10	"role": "assistant",
11	"content": "Panicly blocks risky model traffic before it can create upstream spend."
12	},
13	"finish_reason": "stop"
14	}
15	]
16	}